pptx - Computer Science and Engineering

Report
CSE 486/586 Distributed Systems
Failure Detectors
Steve Ko
Computer Sciences and Engineering
University at Buffalo
CSE 486/586, Spring 2012
Last Time
• Socket programming
– socket(), bind(), listen(), accept(), connect(), read(), write()…
• Android
– Activities, Services, Broadcast receivers, Content providers,
Intents, AndroidManifest.xml
• Overview of the projects
– Project 0: simple messenger
– Project 1 ~ project 3: distributed key-value store
CSE 486/586, Spring 2012
2
Today’s Question
I have a feeling
that something
went wrong…
zzz…
• You’ll learn new terminologies, definitions, etc.
CSE 486/586, Spring 2012
3
Two Different System Models
• Synchronous Distributed System
•
•
•
•
Each message is received within bounded time
Each step in a process takes lb < time < ub
(Each local clock’s drift has a known bound)
Examples: Multiprocessor systems
• Asynchronous Distributed System
• No bounds on message transmission delays
• No bounds on process execution
• (The drift of a clock is arbitrary)
• Examples: Internet, wireless networks, datacenters, most
real systems
• These are used to reason about how protocols would
behave, e.g., in formal proofs.
CSE 486/586, Spring 2012
4
Failure Model
• What is a failure?
• We’ll consider: process omission failure
• A process disappears.
• Permanently: crash-stop (fail-stop) – a process halts and
does not execute any further operations
• Temporarily: crash-recovery – a process halts, but then
recovers (reboots) after a while
• We will focus on crash-stop failures
• They are easy to detect in synchronous systems
• Not so easy in asynchronous systems
• The first step to handle failures?
CSE 486/586, Spring 2012
5
What is a Failure Detector?
pi
pj
CSE 486/586, Spring 2012
6
What is a Failure Detector?
Crash-stop failure
(pj is a failed process)
pi
pj
CSE 486/586, Spring 2012
7
What is a Failure Detector?
needs to know about pj’s failure
(pi is a non-faulty process
or alive process)
Crash-stop failure
(pj is a failed process)
pi
pj
There are two styles of failure detectors
CSE 486/586, Spring 2012
8
I. Ping-Ack Protocol
ping
pi
pj
ack
• pj replies
• pi queries pj once every T
time units
• If pj does not respond
within another T time units
of being sent the ping, pi
detects/declares pj as failed
If pj fails, then within T time units, pi will send
it a ping message. pi will time out within
another T time units.
Worst case Detection time = 2T
The waiting time ‘T’ can be parameterized.
CSE 486/586, Spring 2012
9
II. Heartbeating Protocol
heartbeat
pi
• If pi has not received a new
heartbeat for the past, say 3T
time units, since it received
the last heartbeat, then pi
detects pj as failed
pj
• pj maintains a sequence
number
• pj sends pi a heartbeat with
incremented seq. number
after every T time units
If T ≫ round trip time of messages, then worst case detection time ~ 3T (why?)
The ‘3’ can be changed to any positive number since it is a parameter
CSE 486/586, Spring 2012
10
In a Synchronous System
• The Ping-Ack and Heartbeat failure detectors are
always correct
– Ping-Ack: set waiting time ‘T’ to be > round-trip time upper
bound
– Heartbeat: set waiting time ‘3*T’ to be > round-trip time
upper bound
• The following property is guaranteed:
– If a process pj fails, then pi will detect its failure as long as pi
itself is alive
– Its next ack/heartbeat will not be received (within the
timeout), and thus pi will detect pj as having failed
CSE 486/586, Spring 2012
11
Failure Detector Properties
• What do you mean a failure detector is “correct”?
• Completeness = every process failure is eventually
detected (no misses)
• Accuracy = every detected failure corresponds to a
crashed process (no mistakes)
• What is a protocol that is 100% complete?
• What is a protocol that is 100% accurate?
• Completeness and Accuracy
– Can both be guaranteed 100% in a synchronous distributed
system (with reliable message delivery in bounded time)
– Can never be guaranteed simultaneously in an
asynchronous distributed system
– Why?
CSE 486/586, Spring 2012
12
Completeness and Accuracy in
Asynchronous Systems
• Impossible because of arbitrary message delays,
message losses
– If a heartbeat/ack is dropped (or several are dropped) from
pj, then pj will be mistakenly detected as failed => inaccurate
detection
– How large would the T waiting period in ping-ack or 3*T
waiting period in heartbeating, need to be to obtain 100%
accuracy?
– In asynchronous systems, delay/losses on a network link are
impossible to distinguish from a faulty process
• Heartbeating – satisfies completeness but not
accuracy (why?)
• Ping-Ack – satisfies completeness but not accuracy
(why?)
CSE 486/586, Spring 2012
13
Completeness or Accuracy?
(in Asynchronous System)
• Most failure detector implementations are willing to
tolerate some inaccuracy, but require 100%
completeness.
• Plenty of distributed apps designed assuming 100%
completeness, e.g., p2p systems
– “Err on the side of caution”.
– Processes not “stuck” waiting for other processes
• But it’s ok to mistakenly detect once in a while since
– the victim process need only rejoin as a new process
• Both Hearbeating and Ping-Ack provide
– Probabilistic accuracy (for a process detected as failed, with
some probability close to 1.0 (but not equal), it is true that it
has actually crashed).
CSE 486/586, Spring 2012
14
Failure Detection in a Distributed
System
• That was for one process pj being detected and one
process pi detecting failures
• Let’s extend it to an entire distributed system
• Difference from original failure detection is
– We want failure detection of not merely one process (pj), but
all processes in system
CSE 486/586, Spring 2012
15
CSE 486/586 Administrivia
• Recitations will begin from next Monday.
– Will mainly cover project 0
• Please start doing project 0 now!
– The deadline is 2/6/12 (Monday).
• Please use Piazza; all announcements will go there.
– If you want an invite, let me know.
• Please come to my office during the office hours!
– Give feedback about the class, ask questions, etc.
CSE 486/586, Spring 2012
16
Failure Detection in a Distributed
System
• That was for one process pj being detected and one
process pi detecting failures
• Let’s extend it to an entire distributed system
• Difference from original failure detection is
– We want failure detection of not merely one process (pj), but
all processes in system
• Any idea?
CSE 486/586, Spring 2012
17
Centralized Heartbeat
pj
pj, Heartbeat Seq. l++
pi
Downside?
CSE 486/586, Spring 2012
18
Ring Heartbeat
pj
pj, Heartbeat Seq. l++
pi
Downside?
CSE 486/586, Spring 2012
19
All-to-All Heartbeat
pj, Heartbeat Seq. l++
pj
…
pi
Advantage: Everyone is able to keep track of everyone
Downside?
CSE 486/586, Spring 2012
20
Efficiency of Failure Detector: Metrics
• Bandwidth: the number of messages sent in the
system during steady state (no failures)
– Small is good
• Detection Time
– Time between a process crash and its detection
– Small is good
• Scalability: Given the bandwidth and the detection
properties, can you scale to a 1000 or million nodes?
– Large is good
• Accuracy
– Large is good (lower inaccuracy is good)
CSE 486/586, Spring 2012
21
Accuracy Metrics
• False Detection Rate: Average number of failures
detected per second, when there are in fact no
failures
• Fraction of failure detections that are false
• Tradeoffs: If you increase the T waiting period in
ping-ack or 3*T waiting period in heartbeating what
happens to:
– Detection Time?
– False positive rate?
– Where would you set these waiting periods?
CSE 486/586, Spring 2012
22
Other Types of Failures
• Let’s discuss the other types of failures
• Failure detectors exist for them too (but we won’t
discuss those)
CSE 486/586, Spring 2012
23
Processes and Channels
p roc e sps
p roc e s qs
sen d m
receive
Co m m u ni c a ti on c h a nn e l
Ou tg o i n g m e s sa g e bu ffe r
CSE 486/586, Spring 2012
In co m i n g m e ss a g e bu ffe r
24
Other Failure Types
• Communication omission failures
– Send-omission: loss of messages between the sending
process and the outgoing message buffer (both inclusive)
» What might cause this?
– Channel omission: loss of message in the communication
channel
» What might cause this?
– Receive-omission: loss of messages between the incoming
message buffer and the receiving process (both inclusive)
» What might cause this?
CSE 486/586, Spring 2012
25
Other Failure Types
• Arbitrary failures
– Arbitrary process failure: arbitrarily omits intended
processing steps or takes unintended processing steps.
– Arbitrary channel failures: messages may be corrupted,
duplicated, delivered out of order, incur extremely large
delays; or non-existent messages may be delivered.
• Above two are Byzantine failures, e.g., due to
hackers, man-in-the-middle attacks, viruses, worms,
etc.
• A variety of Byzantine fault-tolerant protocols have
been designed in literature!
CSE 486/586, Spring 2012
26
Omission and Arbitrary Failures
Class of failure Affects
Fail-stop
Process
Omission
Description
Process halts and remains halted. Other processes may
detect this state.
Channel
A message inserted in an outgoing message buffer never
arrives at the other end’s incoming message buffer.
Send-omission Process A process completes asend,but the message is not put
in its outgoing message buffer.
Receive-omissionProcess A message is put in a process’s incoming message
buffer, but that process does not receive it.
Arbitrary
Process or Process/channel exhibits arbitrary behaviour: it may
(Byzantine)
channel send/transmit arbitrary messages at arbitrary times,
commit omissions; a process may stop or take an
incorrect step.
CSE 486/586, Spring 2012
27
Summary
• Failure detectors are required in distributed systems
to keep system running in spite of process crashes
• Properties – completeness & accuracy, together
unachievable in asynchronous systems but
achievable in synchronous systems
– Most apps require 100% completeness, but can tolerate
inaccuracy
• 2 failure detector algorithms - heartbeating and ping
• Distributed FD through heartbeating: centralized,
ring, all-to-all
• Metrics: bandwidth, detection time, scale, accuracy
• Other types of failures
• Next: the notion of time in distributed systems
CSE 486/586, Spring 2012
28
Acknowledgements
• These slides contain material developed and
copyrighted by Indranil Gupta at UIUC.
CSE 486/586, Spring 2012
29

similar documents